plt.show() fig, ax = plt.subplots(1, 1) c, d = 10.5, 4.3 mean, var, skew, kurt = burr.stats(c, d, moments='mvsk') x = np.linspace(burr.ppf(0.01, c, d), burr.ppf(0.99, c, d), 100) burr.ppf print(stats.norm.__doc__) alpha, loc, beta = b[0], b[1], b[2] pdf = nct.pdf() data = ss.genlogistic.rvs(alpha, loc=loc, scale=beta, size=5000) myHist = plt.hist(distribution_car_price, 500, normed=True) rv = ss.genlogistic(alpha, loc, beta) x = np.linspace(0, 500000) h = plt.plot(x, rv.pdf(x), lw=2) axes = plt.gca() axes.set_xlim([0, 150000]) plt.show() alpha, loc, beta = b[0], b[1], b[2] data = ss.genlogistic.rvs(alpha, loc=loc, scale=beta, size=10000) myHist = plt.hist(distribution_car_price, 500, normed=True) rv = ss.nct(a[0], a[1], a[2], a[3]) x = np.linspace(0, 500000) h = plt.plot(x, rv.pdf(x), lw=2) axes = plt.gca()
x = np.linspace(genlogistic.ppf(0.01, c), genlogistic.ppf(0.99, c), 100)
ax.plot(x,
genlogistic.pdf(x, c),
'r-',
lw=5,
alpha=0.6,
label='genlogistic pdf')
# Alternatively, the distribution object can be called (as a function)
# to fix the shape, location and scale parameters. This returns a "frozen"
# RV object holding the given parameters fixed.
# Freeze the distribution and display the frozen ``pdf``:
rv = genlogistic(c)
ax.plot(x, rv.pdf(x), 'k-', lw=2, label='frozen pdf')
# Check accuracy of ``cdf`` and ``ppf``:
vals = genlogistic.ppf([0.001, 0.5, 0.999], c)
np.allclose([0.001, 0.5, 0.999], genlogistic.cdf(vals, c))
# True
# Generate random numbers:
r = genlogistic.rvs(c, size=1000)
# And compare the histogram:
ax.hist(r, density=True, histtype='stepfilled', alpha=0.2)
9.1193851632305201,
261.3457987967214)
drivingduration_model_dict['exponweib'] = st.exponweib(2.6443841639764942,
0.89242254172118096,
10.603640861374947,
40.28556311444698)
drivingduration_model_dict['gengamma'] = st.gengamma(4.8743515108339581,
0.61806208678747043,
9.4649293818479716,
5.431576919220225)
drivingduration_model_dict['recipinvgauss'] = st.recipinvgauss(
0.499908918842556, 0.78319699707613699, 28.725450197674746)
drivingduration_model_dict['f'] = st.f(9.8757694313677113, 12.347442183821462,
0.051160749890587665,
73.072591767722287)
carprice_model_dict = ct.OrderedDict()
carprice_model_dict['nct'] = st.nct(7.3139456577106312, 3.7415255108348946,
-46.285705145385577, 7917.0860181436065)
carprice_model_dict['genlogistic'] = st.genlogistic(10.736440967148635,
3735.7049978006107,
10095.421377235754)
carprice_model_dict['gumbel_r'] = st.gumbel_r(26995.077239517472,
10774.370808211244)
carprice_model_dict['f'] = st.f(24168.523476867485, 35.805656864712923,
-21087.314142557225, 51154.0328397044)
carprice_model_dict['johnsonsu'] = st.johnsonsu(-1.7479864366935538,
1.8675670208081987,
14796.793096897647,
14716.575397771712)
ax1 = fig.add_subplot(1, 2, 1)
sm.qqplot(logeados,
stats.mielke(parametros_mielke[0],
parametros_mielke[1],
loc=parametros_mielke[2],
scale=parametros_mielke[3]),
line="45",
ax=ax1)
ax1.set_title('mielke', size=11.0)
ax1.set_xlabel("")
ax1.set_ylabel("")
ax2 = fig.add_subplot(1, 2, 2)
sm.qqplot(logeados,
stats.genlogistic(parametros_genlogistic[0],
parametros_genlogistic[1],
parametros_genlogistic[2]),
line="45",
ax=ax2)
ax2.set_title('genlogistic', size=11.0)
ax2.set_xlabel("")
ax2.set_ylabel("")
fig.tight_layout(pad=0.7)
fig.text(0.5, 0, 'Cuantiles teóricos', ha='center', va='center')
fig.text(0.,
0.5,
'Cuantiles observados',
ha='center',
va='center',
def all_dists():
# dists param were taken from scipy.stats official
# documentaion examples
# Total - 89
return {
"alpha":
stats.alpha(a=3.57, loc=0.0, scale=1.0),
"anglit":
stats.anglit(loc=0.0, scale=1.0),
"arcsine":
stats.arcsine(loc=0.0, scale=1.0),
"beta":
stats.beta(a=2.31, b=0.627, loc=0.0, scale=1.0),
"betaprime":
stats.betaprime(a=5, b=6, loc=0.0, scale=1.0),
"bradford":
stats.bradford(c=0.299, loc=0.0, scale=1.0),
"burr":
stats.burr(c=10.5, d=4.3, loc=0.0, scale=1.0),
"cauchy":
stats.cauchy(loc=0.0, scale=1.0),
"chi":
stats.chi(df=78, loc=0.0, scale=1.0),
"chi2":
stats.chi2(df=55, loc=0.0, scale=1.0),
"cosine":
stats.cosine(loc=0.0, scale=1.0),
"dgamma":
stats.dgamma(a=1.1, loc=0.0, scale=1.0),
"dweibull":
stats.dweibull(c=2.07, loc=0.0, scale=1.0),
"erlang":
stats.erlang(a=2, loc=0.0, scale=1.0),
"expon":
stats.expon(loc=0.0, scale=1.0),
"exponnorm":
stats.exponnorm(K=1.5, loc=0.0, scale=1.0),
"exponweib":
stats.exponweib(a=2.89, c=1.95, loc=0.0, scale=1.0),
"exponpow":
stats.exponpow(b=2.7, loc=0.0, scale=1.0),
"f":
stats.f(dfn=29, dfd=18, loc=0.0, scale=1.0),
"fatiguelife":
stats.fatiguelife(c=29, loc=0.0, scale=1.0),
"fisk":
stats.fisk(c=3.09, loc=0.0, scale=1.0),
"foldcauchy":
stats.foldcauchy(c=4.72, loc=0.0, scale=1.0),
"foldnorm":
stats.foldnorm(c=1.95, loc=0.0, scale=1.0),
# "frechet_r": stats.frechet_r(c=1.89, loc=0.0, scale=1.0),
# "frechet_l": stats.frechet_l(c=3.63, loc=0.0, scale=1.0),
"genlogistic":
stats.genlogistic(c=0.412, loc=0.0, scale=1.0),
"genpareto":
stats.genpareto(c=0.1, loc=0.0, scale=1.0),
"gennorm":
stats.gennorm(beta=1.3, loc=0.0, scale=1.0),
"genexpon":
stats.genexpon(a=9.13, b=16.2, c=3.28, loc=0.0, scale=1.0),
"genextreme":
stats.genextreme(c=-0.1, loc=0.0, scale=1.0),
"gausshyper":
stats.gausshyper(a=13.8, b=3.12, c=2.51, z=5.18, loc=0.0, scale=1.0),
"gamma":
stats.gamma(a=1.99, loc=0.0, scale=1.0),
"gengamma":
stats.gengamma(a=4.42, c=-3.12, loc=0.0, scale=1.0),
"genhalflogistic":
stats.genhalflogistic(c=0.773, loc=0.0, scale=1.0),
"gilbrat":
stats.gilbrat(loc=0.0, scale=1.0),
"gompertz":
stats.gompertz(c=0.947, loc=0.0, scale=1.0),
"gumbel_r":
stats.gumbel_r(loc=0.0, scale=1.0),
"gumbel_l":
stats.gumbel_l(loc=0.0, scale=1.0),
"halfcauchy":
stats.halfcauchy(loc=0.0, scale=1.0),
"halflogistic":
stats.halflogistic(loc=0.0, scale=1.0),
"halfnorm":
stats.halfnorm(loc=0.0, scale=1.0),
"halfgennorm":
stats.halfgennorm(beta=0.675, loc=0.0, scale=1.0),
"hypsecant":
stats.hypsecant(loc=0.0, scale=1.0),
"invgamma":
stats.invgamma(a=4.07, loc=0.0, scale=1.0),
"invgauss":
stats.invgauss(mu=0.145, loc=0.0, scale=1.0),
"invweibull":
stats.invweibull(c=10.6, loc=0.0, scale=1.0),
"johnsonsb":
stats.johnsonsb(a=4.32, b=3.18, loc=0.0, scale=1.0),
"johnsonsu":
stats.johnsonsu(a=2.55, b=2.25, loc=0.0, scale=1.0),
"ksone":
stats.ksone(n=1e03, loc=0.0, scale=1.0),
"kstwobign":
stats.kstwobign(loc=0.0, scale=1.0),
"laplace":
stats.laplace(loc=0.0, scale=1.0),
"levy":
stats.levy(loc=0.0, scale=1.0),
"levy_l":
stats.levy_l(loc=0.0, scale=1.0),
"levy_stable":
stats.levy_stable(alpha=0.357, beta=-0.675, loc=0.0, scale=1.0),
"logistic":
stats.logistic(loc=0.0, scale=1.0),
"loggamma":
stats.loggamma(c=0.414, loc=0.0, scale=1.0),
"loglaplace":
stats.loglaplace(c=3.25, loc=0.0, scale=1.0),
"lognorm":
stats.lognorm(s=0.954, loc=0.0, scale=1.0),
"lomax":
stats.lomax(c=1.88, loc=0.0, scale=1.0),
"maxwell":
stats.maxwell(loc=0.0, scale=1.0),
"mielke":
stats.mielke(k=10.4, s=3.6, loc=0.0, scale=1.0),
"nakagami":
stats.nakagami(nu=4.97, loc=0.0, scale=1.0),
"ncx2":
stats.ncx2(df=21, nc=1.06, loc=0.0, scale=1.0),
"ncf":
stats.ncf(dfn=27, dfd=27, nc=0.416, loc=0.0, scale=1.0),
"nct":
stats.nct(df=14, nc=0.24, loc=0.0, scale=1.0),
"norm":
stats.norm(loc=0.0, scale=1.0),
"pareto":
stats.pareto(b=2.62, loc=0.0, scale=1.0),
"pearson3":
stats.pearson3(skew=0.1, loc=0.0, scale=1.0),
"powerlaw":
stats.powerlaw(a=1.66, loc=0.0, scale=1.0),
"powerlognorm":
stats.powerlognorm(c=2.14, s=0.446, loc=0.0, scale=1.0),
"powernorm":
stats.powernorm(c=4.45, loc=0.0, scale=1.0),
"rdist":
stats.rdist(c=0.9, loc=0.0, scale=1.0),
"reciprocal":
stats.reciprocal(a=0.00623, b=1.01, loc=0.0, scale=1.0),
"rayleigh":
stats.rayleigh(loc=0.0, scale=1.0),
"rice":
stats.rice(b=0.775, loc=0.0, scale=1.0),
"recipinvgauss":
stats.recipinvgauss(mu=0.63, loc=0.0, scale=1.0),
"semicircular":
stats.semicircular(loc=0.0, scale=1.0),
"t":
stats.t(df=2.74, loc=0.0, scale=1.0),
"triang":
stats.triang(c=0.158, loc=0.0, scale=1.0),
"truncexpon":
stats.truncexpon(b=4.69, loc=0.0, scale=1.0),
"truncnorm":
stats.truncnorm(a=0.1, b=2, loc=0.0, scale=1.0),
"tukeylambda":
stats.tukeylambda(lam=3.13, loc=0.0, scale=1.0),
"uniform":
stats.uniform(loc=0.0, scale=1.0),
"vonmises":
stats.vonmises(kappa=3.99, loc=0.0, scale=1.0),
"vonmises_line":
stats.vonmises_line(kappa=3.99, loc=0.0, scale=1.0),
"wald":
stats.wald(loc=0.0, scale=1.0),
"weibull_min":
stats.weibull_min(c=1.79, loc=0.0, scale=1.0),
"weibull_max":
stats.weibull_max(c=2.87, loc=0.0, scale=1.0),
"wrapcauchy":
stats.wrapcauchy(c=0.0311, loc=0.0, scale=1.0),
}
def execute_scoring(self):
# Compile scoring configuration parameters
scoring_config = {
'posteriors':
self.run_config['posteriors'],
'hdsl':
self.run_config['HDSL'],
'spp':
self.run_config['SPP'],
'viterbi':
self.run_config['viterbi'],
'suppress_nan':
True,
'fp_posteriors':
os.path.join(self.run_config['output'], 'posteriors.txt'),
'fp_scores_pre':
os.path.join(self.run_config['output'], 'scores_pre'),
'fp_scores':
os.path.join(self.run_config['output'], 'scores.txt'),
'fp_hdsl':
os.path.join(self.run_config['output'], 'hdsl.txt'),
'fp_spp':
os.path.join(self.run_config['output'], 'spp.txt'),
'fp_viterbi':
os.path.join(self.run_config['output'], 'viterbi.txt'),
'no_cscores':
self.run_config['no_cscores'],
'min_cscores':
self.run_config['min_cscores'],
'batch_size':
self.run_config['batch_size'],
'motifs':
self.motifs,
'path':
self.run_config['path'],
'context':
self.run_config['context'],
'cscore_dists':
None,
'no_vienna':
self.no_vienna,
'energy':
~np.any([
self.no_vienna, self.run_config['no_cscores'],
not viennalib.vienna_imported
]),
'lbc':
self.lbc,
'hdsl_params':
self.run_config['hdsl_params']
}
self.pool_init() # Initialize parallelized pool
# Prepare score distributions for c-score normalization
if not scoring_config['no_cscores']:
logger.info('Sampling null sites for c-score normalization')
clock.tick()
self.cscore_dists = dict.fromkeys(self.motifs)
cscore_batch = self.make_cscore_batch(
scoring_config['min_cscores'])
cscore_batch.pre_process(self.model, scoring=True)
with tqdm(total=len(self.motifs), leave=False,
unit='motif') as pb_samples:
try:
if scoring_config['path']:
path = np.array(list(scoring_config['path']),
dtype=int)
else:
path = None
worker = partial(self.sample_worker,
path=path,
batch=cscore_batch)
samples_pool = self.mp_pool.imap_unordered(
worker, self.motifs)
for (motif, samples) in samples_pool:
params = genlogistic.fit(samples)
self.cscore_dists[motif] = genlogistic(c=params[0],
loc=params[1],
scale=params[2])
pb_samples.update()
self.mp_pool.close()
self.mp_pool.join()
except Exception:
self.mp_pool.terminate()
raise
scoring_config['cscore_dists'] = self.cscore_dists
logger.info(' ... done in {}'.format(
misclib.seconds_to_hms(clock.tock())))
# Begin formal scoring phase by making batches to save on memory
batches = self.make_batches(scoring_config['batch_size'])
n_batches = len(self.dataset.rnas) // scoring_config[
'batch_size'] + 1 # Number of batches
if self.motifs:
header = "transcript\tstart score c-score BCE MEL Prob(motif) motif path seq\n"
with open(scoring_config['fp_scores_pre'], 'w') as f:
f.write(header)
logger.info("Executing scoring")
clock.tick()
with tqdm(total=n_batches,
leave=False,
unit='batch',
desc=' Overall') as pbar_batches:
# Process batches sequentially
for i, batch in enumerate(batches):
self.pool_init()
batch.pre_process(self.model)
with tqdm(total=len(batch.rnas),
leave=False,
unit="transcript",
desc="Current batch") as pbar_transcripts:
try:
worker = partial(self.score_worker,
model=self.model,
config=scoring_config)
jobs = self.mp_pool.imap_unordered(
worker, batch.rnas.values())
for _ in jobs:
pbar_transcripts.update()
self.mp_pool.close()
self.mp_pool.join()
except Exception:
self.mp_pool.terminate()
raise
batch.clear()
pbar_batches.update()
# Sort score file
if self.motifs:
scores = filelib.read_score_file(scoring_config['fp_scores_pre'])
if not scores:
os.rename(scoring_config['fp_scores_pre'],
scoring_config['fp_scores'])
else:
if scoring_config['no_cscores']:
filelib.write_score_file(
sorted(scores,
key=lambda score: score['score'],
reverse=True), scoring_config['fp_scores'])
else:
if scoring_config['energy']:
filelib.write_score_file(
sorted(scores,
key=lambda score: score['Prob(motif)'],
reverse=True), scoring_config['fp_scores'])
else:
filelib.write_score_file(
sorted(scores,
key=lambda score: score['c-score'],
reverse=True), scoring_config['fp_scores'])
os.remove(scoring_config['fp_scores_pre']) # Clean-up
logger.info(' ... done in {}'.format(
misclib.seconds_to_hms(clock.tock())))